Insurance
25 columns
200 rows
8 formats

Medical Claims Fraud Detection

This dataset contains detailed records of healthcare insurance claims, including patient, provider, policy, and transaction information, along with fraud detection indicators and review outcomes. It enables insurers and healthcare analytics teams to identify fraudulent patterns, minimize financial losses, and maintain regulatory compliance through comprehensive claim-level analysis.

opened 8 times
last updated 20 Aug 2025
by GoMask

The brief that made it

Automated detection of fraudulent insurance claims

Sample rows

preview · 8 of 200 rows · all 25 columns

claim_idstring	claim_statusstring	fraud_scorefloat	fraud_flagboolean	provider_statestring	patient_idstring	provider_idstring	policy_idstring	claim_datedate	service_datedate	diagnosis_codestring	procedure_codestring	claim_amountfloat	approved_amountfloat	reviewed_bystring	review_datedate	patient_dobdate	patient_genderstring	provider_namestring	provider_specialtystring	provider_street_addressstring	provider_citystring	provider_postal_codestring	provider_countrystring	notesstring
CLM000001	approved	0.12	false	CA	PAT1001	PRV2001	POL3001	2024-04-10	2024-04-08	E11.9	99213	145	145	JSMITH09	2024-04-12	1988-07-16	female	Metro Family Clinic	general practice	812 Oak Ave	Los Angeles	90015	USA	Routine diabetes checkup for established patient.
CLM000002	approved	0.09	false	TX	PAT1002	PRV2002	POL3002	2024-03-23	2024-03-21	J45.909	94640	75.5	75.5	MARQUEZ1	2024-03-24	2012-02-09	male	ChildCare Pediatrics Center	pediatrics	624 Maple St	Dallas	75204	USA	Asthma inhalation therapy during pediatric exam.
CLM000003	approved	0.05	false	MN	PAT1003	PRV2003	POL3003	2024-02-15	2024-02-13	I10	93000	90	90	KLEE12	2024-02-16	1953-11-25	female	St. Paul Cardiology Group	cardiology	1477 Grand Ave	St. Paul	55105	USA	EKG performed due to hypertension diagnosis.
CLM000004	approved	0.11	false	NC	PAT1004	PRV2004	POL3004	2024-03-07	2024-03-05	F33.1	90834	120.5	120.5	AMARTIN3	2024-03-09	1995-08-03	female	Central Mental Wellness Center	mental health	334 Ashland Dr	Charlotte	28203	USA	Psychotherapy session for moderate depression.
CLM000005	approved	0.17	false	MN	PAT1005	PRV2005	POL3005	2024-05-02	2024-04-30	S83.001A	27370	250	250	SYS_AUTOMATED	2024-05-03	1978-06-14	male	NorthStar Orthopedic Group	orthopedics	2551 Willow Rd	Minneapolis	55401	USA	Knee injection for meniscus tear; outpatient procedure.
CLM000006	approved	0.06	false	CA	PAT1006	PRV2006	POL3006	2024-01-18	2024-01-16	H52.4	92015	65	65	EGRANT81	2024-01-19	2008-12-01	other	VisionCare Optometry Center	optometry	6749 Pine St	San Francisco	94118	USA	Annual vision test for child patient.
CLM000007	approved	0.03	false	MA	PAT1007	PRV2007	POL3007	2024-04-25	2024-04-23	Z00.00	99385	40	40	SYS_AUTOMATED	2024-04-26	2016-03-20	female	Westside Pediatrics Clinic	pediatrics	1022 Elm St	Boston	02116	USA	Well-child checkup for new patient.
CLM000008	approved	0.19	false	CA	PAT1008	PRV2008	POL3008	2024-02-28	2024-02-27	M54.5	97110	180	180	JROBERTS4	2024-02-29	1974-05-10	unknown	East Bay Rehab Center	physical therapy	4500 Bridge Rd	Oakland	94612	USA	Physical therapy for lower back pain.
CLM000009	approved	0.15	false	TX	PAT1009	PRV2009	POL3009	2024-05-10	2024-05-08	E78.5	80061	210	210	SYS_AUTOMATED	2024-05-11	1999-09-13	male	South Texas Preventive Group	preventive medicine	9112 Cedar Dr	Houston	77004	USA	Routine cholesterol panel during annual physical.
CLM000010	approved	0.08	false	TX	PAT1010	PRV2010	POL3010	2024-03-18	2024-03-16	R51	96372	30	30	BWILLIAMS	2024-03-19	2005-01-27	female	Green Valley Family Center	general practice	3892 Birch Pl	Austin	78701	USA	Migraine injection for teenager; outpatient.
CLM000011	rejected	0.29	false	IL	PAT1011	PRV2011	POL3011	2024-04-16	2024-04-15	J06.9	99214	40	0	SYS_AUTOMATED	2024-04-17	2014-05-14	male	Urban Pediatrics Associates	pediatrics	675 Oakbrook Dr	Chicago	60607	USA	Claim rejected due to duplicate submission.
CLM000012	rejected	0.25	false	MO	PAT1012	PRV2012	POL3012	2024-05-14	2024-05-12	M25.561	20610	165.75	0	SYS_AUTOMATED	2024-05-15	1962-02-24	female	Midwest Joint Clinic	orthopedics	1142 Cypress Ln	Kansas City	64108	USA	Rejected for lack of prior authorization.
CLM000013	approved	0.18	false	CA	PAT1013	PRV2013	POL3013	2024-03-02	2024-03-01	F41.1	90837	600	600	TJOHNSON7	2024-03-03	1982-11-02	male	Pacific Mental Health Clinic	mental health	3400 Mission St	San Francisco	94110	USA	Extended counseling for anxiety disorder.
CLM000014	approved	0.13	false	FL	PAT1014	PRV2014	POL3014	2024-02-20	2024-02-19	C50.911	19120	4950	4950	LPOWELL20	2024-02-21	1969-03-28	female	Care Oncology Center	oncology	8100 Sunrise Blvd	Orlando	32801	USA	Lumpectomy for confirmed breast cancer diagnosis.
CLM000015	approved	0.14	false	CA	PAT1015	PRV2015	POL3015	2024-03-29	2024-03-27	K21.9	43239	850	850	JLEE22	2024-03-30	1957-06-09	male	Bayview Gastroenterology Group	gastroenterology	2301 Park Ave	San Diego	92101	USA	Endoscopy for chronic reflux symptoms.
CLM000016	under_review	0.81	true	NC	PAT1016	PRV2016	POL3016	2024-01-24	2024-01-22	G40.909	95951	3700.8	0	DTHOMAS16	2024-01-29	1961-10-14	male	Neurology Institute of Raleigh	neurology	1500 Wake Forest Rd	Raleigh	27609	USA	Claim flagged for review due to atypically high EEG charges.
CLM000017	submitted	0.01	false	CA	PAT1017	PRV2017	POL3017	2024-05-05	2024-05-03	B34.9	87880	0	0	blank	blank	2018-11-23	female	TeleClinic Health	telemedicine	1200 Virtual Pkwy	San Jose	95110	USA	COVID screening tele-visit; initial claim submitted.
CLM000018	rejected	0.32	false	TX	PAT1018	PRV2018	POL3018	2024-03-12	2024-03-10	N39.0	81002	30	0	SYS_AUTOMATED	2024-03-13	2009-04-18	male	UrgentMed Express Center	urgent care	7411 Main St	Houston	77002	USA	Rejected; claim incomplete urinalysis details.
CLM000019	under_review	0.92	true	IL	PAT1019	PRV2019	POL3019	2024-04-01	2024-03-31	E66.9	43644	15580	0	HROGERS11	2024-04-06	1972-09-04	female	Bariatric Surgery Center	bariatric surgery	3400 Health Dr	Chicago	60618	USA	High-value claim flagged for potential upcoding.
CLM000020	approved	0.09	false	NC	PAT1020	PRV2020	POL3020	2024-02-01	2024-01-30	M16.9	27130	5900	5900	KADAMS24	2024-02-03	1959-08-27	male	Charlotte Ortho Hospital	orthopedics	4301 Freedom Dr	Charlotte	28208	USA	Total hip replacement for chronic osteoarthritis.

What the 200 rows show

from the 200-row sample

Rejected (claim status) stands out: mean fraud_score is 0.44, against 0.15 for the rest.

10%fraud_flag = true
0.11median fraud_score
4patient genders
43provider specialties
50provider cities
120.5median claim_amount

Mean fraud_score by claim_status200 rows

fraud_score200 rows, in bands of 0.1

Every row with fraud_score of 0.7 or more has fraud_flag = true. None below it.

provider_state200 rows · top 10 of 28 values

CA45
TX30
MA13
NC12
WA11
FL10
MN8
CO8
OH8
IL7

25 columns by typefrom the column list below

string 17
float 3
date 4
boolean 1

Columns

25 columns in four groups

blueprint · 25 columns
column	type	description	example
Text 17 columns
`claim_id`	string	Unique identifier for each insurance claimunique	CLM000001
`patient_id`	string	Unique identifier for the patient associated with the claim	PAT1001
`provider_id`	string	Unique identifier for the healthcare provider submitting the claim	PRV2001
`policy_id`	string	Unique identifier for the insurance policy under which the claim is filed	POL3001
`diagnosis_code`	string	Standardized code representing the diagnosis (e.g., ICD-10)	E11.9
`procedure_code`	string	Standardized code representing the procedure performed (e.g., CPT)	99213
`claim_status`	string	Current status of the claim (e.g., submitted, approved, rejected, under_review)submitted · approved · rejected · under_review	approved
`reviewed_by`	string	Identifier for the analyst or system that reviewed the claim for fraudoptional	JSMITH09
`patient_gender`	string	Gender of the patientmale · female · other · unknown · optional	female
`provider_name`	string	Name of the healthcare provideroptional	Metro Family Clinic
`provider_specialty`	string	Medical specialty of the provider (e.g., cardiology, general practice)optional	general practice
`provider_street_address`	string	Street address of the healthcare provideroptional	812 Oak Ave
`provider_city`	string	City of the healthcare provideroptional	Los Angeles
`provider_state`	string	State of the healthcare provideroptional	CA
`provider_postal_code`	string	Postal code of the healthcare provideroptional	90015
`provider_country`	string	Country of the healthcare provideroptional	USA
`notes`	string	Additional notes or comments about the claim or fraud reviewoptional	Routine diabetes checkup …
Numbers 3 columns
`claim_amount`	float	Total amount claimed for reimbursement0 or more	145
`approved_amount`	float	Amount approved by the insurer for reimbursement0 or more · optional	145
`fraud_score`	float	Numerical score indicating likelihood of fraud (0-1, higher means more likely)0 to 1 · optional	0.12
Dates and times 4 columns
`claim_date`	date	Date when the claim was submitted	2024-04-10
`service_date`	date	Date when the medical service was provided	2024-04-08
`review_date`	date	Date when the claim was reviewed for fraudoptional	2024-04-12
`patient_dob`	date	Date of birth of the patient	1988-07-16
True or false 1 column
`fraud_flag`	boolean	Indicates whether the claim is suspected or confirmed as fraudulent	false

Use it for

An insurance dashboard
The fraud_flag rate, fraud_score by claim_status and a breakdown of provider_state. Excel, Power BI or Tableau.
Why do the 20 rejected rows have a mean fraud_score of 0.44?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Claims200
CLM0000010.12approved
CLM0000160.81under_re…
CLM0000190.92under_re…
A software demo
Believable claims with patient_id, provider_id and policy_id to fill a screen in front of a buyer.

This dataset200 rows25 columns

Yours1,000 rows25 columnsprovider_street_address: UK only

blueprint · medical-claims-fraud-detection

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 25 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with

Claims must include patient, provider, and service codes
Flag claims exceeding regional average costs
Check for duplicated services within 30 days
Validate provider license status before approval

Rows1,000 rows10,000 rows100,000 rows1,000,000 rows

Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports: CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence: yours to use, including commercially
API slug: medical-claims-fraud-detection

What should your data show?

No signup. No card.

Sample rows

What the 200 rows show

Columns

Use it for

An insurance dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Insurance

What should your data show?